© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125693
    Prev
    Next
    INDEX
    Explanations

    connections and comparisons between different ideas or concepts in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation and connector words (like "so", "thus", "for example") that introduce explanations or examples after a general statement.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zet
    -0.06
    سÙĬ
    -0.06
    ippo
    -0.06
    fit
    -0.06
    ennen
    -0.06
     Lambert
    -0.06
    pill
    -0.06
    fits
    -0.05
     penetr
    -0.05
    ÑĤÑİ
    -0.05
    POSITIVE LOGITS
     if
    0.20
     If
    0.18
    If
    0.17
     wenn
    0.15
    å¦Ĥæŀľ
    0.15
     jika
    0.14
     when
    0.14
     nếu
    0.14
     еÑģли
    0.14
    	if
    0.14
    Activations Density 0.112%

    No Known Activations